Research map / Vision-language and multimodal / Cross-modal learning
Efficient Modality Selection in Multimodal Learning
Yifei He, Runxiang Cheng, Gargi Balasubramaniam, Yao-Hung Hubert Tsai, Han Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use greedy submodular selection (Algorithm 1) instead of random selection | modality selection · Patch-MNIST (49 and 9 modalities) | utility / test accuracy | Improved |
| use greedy selection instead of the average subset | modality selection · Patch-MNIST (9 modalities) | utility | Improved |
| select with greedy Algorithm 1 | modality selection · Patch-MNIST (49 modalities) | utility: near-maximum utility with 7 modalities | Improved |
| add modalities beyond 20 selected | modality selection · Patch-MNIST (49 modalities) | test accuracy: accuracy barely improves after 20 modalities | No clear effect |
| use greedy Algorithm 1 instead of MCI ranking | modality selection · Patch-MNIST (49 modalities) | test loss: slightly lower loss below size 15 | Mixed |
| use MCI ranking instead of greedy maximization | modality selection · Patch-MNIST (9 modalities) | utility | No clear effect |
Closest papers by meaning
- Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning (NeurIPS 2025 · similarity 0.90)
- Enhancing Multimodal Cooperation via Sample-level Modality Valuation (CVPR 2024 · similarity 0.90)
- Asymmetric Reinforcing Against Multi-Modal Representation Bias (AAAI 2025 · similarity 0.89)
- Continual Multimodal Contrastive Learning (NeurIPS 2025 · similarity 0.89)
- Facilitating Multimodal Classification via Dynamically Learning Modality Gap (NeurIPS 2024 · similarity 0.89)
- Beyond Modality Fusion: Deep Ensembles for Multimodal Classification (NeurIPS 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
